Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 12579
    Prev
    Next
    INDEX
    Explanations

    references to specific biochemical compounds and their properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    usk
    -0.59
    دار
    -0.59
     Nair
    -0.58
     loc
    -0.58
     “
    -0.57
    רט
    -0.54
     &'
    -0.54
     tre
    -0.53
     Turki
    -0.52
    وف
    -0.52
    POSITIVE LOGITS
     omega
    1.31
     Omega
    1.29
     Lambda
    1.18
     DELTA
    1.16
     epsilon
    1.13
    omega
    1.12
     Epsilon
    1.12
     gamma
    1.11
    MEGA
    1.10
     Gamma
    1.10
    Activations Density 0.478%

    No Known Activations